Geekbench ML Score

1399
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 09:25 AM
Views 1

System Information

System Information
Operating System iOS 14.7.1
Model iPhone SE (2nd generation)
Model IDiPhone12,8
Motherboard D79AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.89 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1634
175.1 IPS
 
Image Classification (F16)
100% 1684
180.4 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 3461
21.4 IPS
 
Image Segmentation (F16)
100% 5427
33.5 IPS
 
Image Segmentation (I8)
89% 828
5.12 IPS
 
Pose Estimation (F32)
100% 1424
5.76 IPS
 
Pose Estimation (F16)
100% 4438
18.0 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
100% 1553
54.5 IPS
 
Object Detection (F16)
99% 1868
65.6 IPS
 
Object Detection (I8)
52% 628
22.0 IPS
 
Face Detection (F32)
100% 3638
41.8 IPS
 
Face Detection (F16)
97% 5186
59.6 IPS
 
Face Detection (I8)
75% 567
6.51 IPS
 
Text Classification (F32)
100% 988
390.7 IPS
 
Text Classification (F16)
98% 1232
487.1 IPS
 
Machine Translation (F32)
100% 1207
186.0 IPS
 
Machine Translation (F16)
100% 1196
184.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download